AI Engineer- RAG and AI Agents
Description
Title: AI Engineer- RAG and AI Agents
Location: PHX, AZ - Onsite (Locals or within MST zone only)
Contract - C2C.
POSITION OVERVIEW:
We are seeking an AI Engineer to design, build, and deploy retrieval-augmented generation (RAG) systems and
intelligent AI agents. This role will focus on developing reliable, scalable AI applications that can retrieve knowledge,
reason over information, use external tools, and automate complex workflows.
The ideal candidate combines strong software engineering skills with hands-on experience in large language
models, vector databases, prompt engineering, agent orchestration, and production AI systems.
KEY RESPONSIBILITIES:
Design and develop RAG pipelines for enterprise documents, structured data, and knowledge bases.
Build AI agents capable of planning, reasoning, using tools, and completing multi-step tasks.
Integrate large language models from providers such as OpenAI, Anthropic, or open-source platforms.
Develop document ingestion, chunking, embedding, indexing, retrieval, and reranking workflows.
Work with vector databases such as Pinecone, Weaviate, Milvus, Qdrant, or pgvector.
Implement agent frameworks and orchestration workflows using tools such as LangChain, LangGraph,
LlamaIndex, or comparable technologies.
Connect AI systems to APIs, databases, business applications, and internal tools.
Improve response accuracy, relevance, latency, cost, and reliability.
Create evaluation frameworks for retrieval quality, hallucination detection, agent performance, and end-to-end
outcomes.
Implement security, access controls, observability, guardrails, and human-in-the-loop workflows.
Collaborate with product, engineering, data, and domain experts to identify high-value AI use cases.
Deploy and maintain AI applications in cloud or containerized environments.
REQUIRED QUALIFICATIONS:
3+ years of experience in software engineering, machine learning engineering, or a related field.
Strong Python programming skills and experience building production APIs or services.
Hands-on experience building and deploying RAG applications.
Practical knowledge of embeddings, semantic search, hybrid search, reranking, and vector databases.
Experience working with LLM APIs, prompt design, structured outputs, and function/tool calling.
Experience developing AI agents or multi-step LLM workflows.
Understanding of data preprocessing, document parsing, metadata management, and knowledge
representation.
Experience with REST APIs, databases, Git, testing, and software development best practices.
Familiarity with cloud platforms such as AWS, Azure, or Google Cloud.
Strong problem-solving, communication, and analytical skills.
PREFERRED QUALIFICATIONS:
Experience with LangGraph, LangChain, LlamaIndex, Semantic Kernel, or similar frameworks.
Experience with agent memory, planning, reflection, routing, and workflow orchestration.
Knowledge of model fine-tuning, reinforcement learning, or evaluation methodologies.
Experience with Kubernetes, Docker, CI/CD, and infrastructure as code.
Familiarity with ML observability and tracing tools such as LangSmith, Arize, Weights & Biases, or Phoenix.
Experience implementing AI safety, privacy, governance, and security controls.
Background in enterprise search, customer support automation, workflow automation, or conversational AI.
TECHNICAL SKILLS:
Python, SQL, REST APIs
LLMs and generative AI
RAG architecture and information retrieval
Embeddings and vector search
Prompt engineering and function calling
AI agents and workflow orchestration
PostgreSQL, vector databases, and data pipelines
Docker, cloud services, and CI/CD
Testing, monitoring, evaluation, and observability"
Skills
- Agentic AI
- AI
- Anthropic
- API
- Automation
- AWS
- Azure
- CI/CD
- Cloud
- Conversational AI
- Data Pipelines
- Docker
- Embeddings
- Fine Tuning
- GCP
- Generative AI
- Git
- Infrastructure as Code
- Kubernetes
- LangChain
- LangGraph
- LangSmith
- LlamaIndex
- LLM
- Machine Learning
- Metadata Management
- Milvus
- Observability
- OpenAI
- pgvector
- Pinecone
- PostgreSQL
- Prompt Engineering
- Python
- Qdrant
- RAG
- Reinforcement Learning
- REST
- Semantic Kernel
- Semantic Search
- SQL
- Vector Databases
- Vector Search
- Weaviate
- Workflow Orchestration
Sign in to read and join the discussion.